RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

Can Granite 3.1 3B A800M Instruct run on the RX 7800 XT?

Yes. At 8K context the best fit is F16, using about 7.1 GB of the 15.2 GB usable on the RX 7800 XT. Estimated speed ceiling: ~353 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •1.9 GB Fits2.1 GB Fits3.6 GB Fits9.6 GB Fits1878
3-bit (Q3_K_M) •2.2 GB Fits2.5 GB Fits4.0 GB Fits10.0 GB Fits1447
4-bit (Q4_K_M) •2.6 GB Fits2.9 GB Fits4.4 GB Fits10.4 GB Fits1156
5-bit (Q5_K_M) •2.9 GB Fits3.2 GB Fits4.7 GB Fits10.7 GB Fits990
6-bit (Q6_K) •3.3 GB Fits3.5 GB Fits5.0 GB Fits11.0 GB Fits859
8-bit (Q8_0) •4.0 GB Fits4.3 GB Fits5.8 GB Fits11.8 GB Fits664
16-bit (F16/BF16) •6.9 GB Fits7.1 GB Fits8.6 GB Fits14.6 GB Tight353

• real GGUF file size from bartowski/granite-3.1-3b-a800m-instruct-GGUF. Speed is a bandwidth ceiling (624 GB/s), not a benchmark. Methodology.

What fits instead

"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.

More

Granite 3.1 3B A800M Instruct on every GPU and Mac · Every model that runs on the RX 7800 XT · Other models that fit 16 GB VRAM · Try other settings in the calculator

Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs

Data: Hugging Face Hub (ibm-granite/granite-3.1-3b-a800m-instruct), AMD specs. Model data last checked 2026-11-18; refreshed hourly.